© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 19309
    Prev
    Next
    INDEX
    Explanations

    terms related to power plants and industrial accidents

    oai_token-act-pair · gpt-3.5-turbo

    references to various facilities and structures related to infrastructure and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynes
    -0.77
    alys
    -0.73
    alle
    -0.72
    brew
    -0.70
    omatic
    -0.68
    matter
    -0.68
    pmwiki
    -0.67
    isol
    -0.66
    aez
    -0.66
    dos
    -0.66
    POSITIVE LOGITS
     fame
    0.76
    eers
    0.76
     located
    0.74
     championed
    0.73
     headquartered
    0.70
     presided
    0.69
     pictured
    0.66
     respectively
    0.65
     spearheaded
    0.64
     Reno
    0.63
    Activations Density 0.429%

    No Known Activations